Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,005 Bytes
38e3f9b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# MIT License
# Copyright (c) 2022 Intelligent Systems Lab Org
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# File author: Shariq Farooq Bhat
import os
import numpy as np
import torch
from PIL import Image
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms
class ToTensor(object):
def __init__(self, resize_shape):
# self.normalize = transforms.Normalize(
# mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
self.normalize = lambda x : x
self.resize = transforms.Resize(resize_shape)
def __call__(self, sample):
image, depth = sample['image'], sample['depth']
image = self.to_tensor(image)
image = self.normalize(image)
depth = self.to_tensor(depth)
image = self.resize(image)
return {'image': image, 'depth': depth, 'dataset': "ddad"}
def to_tensor(self, pic):
if isinstance(pic, np.ndarray):
img = torch.from_numpy(pic.transpose((2, 0, 1)))
return img
# # handle PIL Image
if pic.mode == 'I':
img = torch.from_numpy(np.array(pic, np.int32, copy=False))
elif pic.mode == 'I;16':
img = torch.from_numpy(np.array(pic, np.int16, copy=False))
else:
img = torch.ByteTensor(
torch.ByteStorage.from_buffer(pic.tobytes()))
# PIL image mode: 1, L, P, I, F, RGB, YCbCr, RGBA, CMYK
if pic.mode == 'YCbCr':
nchannel = 3
elif pic.mode == 'I;16':
nchannel = 1
else:
nchannel = len(pic.mode)
img = img.view(pic.size[1], pic.size[0], nchannel)
img = img.transpose(0, 1).transpose(0, 2).contiguous()
if isinstance(img, torch.ByteTensor):
return img.float()
else:
return img
class DDAD(Dataset):
def __init__(self, data_dir_root, resize_shape):
import glob
# image paths are of the form <data_dir_root>/{outleft, depthmap}/*.png
self.image_files = glob.glob(os.path.join(data_dir_root, '*.png'))
self.depth_files = [r.replace("_rgb.png", "_depth.npy")
for r in self.image_files]
self.transform = ToTensor(resize_shape)
def __getitem__(self, idx):
image_path = self.image_files[idx]
depth_path = self.depth_files[idx]
image = np.asarray(Image.open(image_path), dtype=np.float32) / 255.0
depth = np.load(depth_path) # meters
# depth[depth > 8] = -1
depth = depth[..., None]
sample = dict(image=image, depth=depth)
sample = self.transform(sample)
if idx == 0:
print(sample["image"].shape)
return sample
def __len__(self):
return len(self.image_files)
def get_ddad_loader(data_dir_root, resize_shape, batch_size=1, **kwargs):
dataset = DDAD(data_dir_root, resize_shape)
return DataLoader(dataset, batch_size, **kwargs)
|